mirror/php-htmlpurifier
1
0
Fork 0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2025-07-30 19:00:10 +02:00
Code Issues Releases Wiki Activity

Remove trailing whitespace.

Browse Source 
Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>
This commit is contained in:
Edward Z. Yang
2008-12-06 02:28:20 -05:00
parent 3a6b63dff1
commit 2c955af135
476 changed files with 5595 additions and 5547 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
library/HTMLPurifier/Encoder.php
View File

@@ -6,31 +6,31 @@
*/
class HTMLPurifier_Encoder
{
/**
* Constructor throws fatal error if you attempt to instantiate class
*/
private function __construct() {
trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
}
/**
* Error-handler that mutes errors, alternative to shut-up operator.
*/
private static function muteErrorHandler() {}
/**
* Cleans a UTF-8 string for well-formedness and SGML validity
*
*
* It will parse according to UTF-8 and return a valid UTF8 string, with
* non-SGML codepoints excluded.
*
*
* @note Just for reference, the non-SGML code points are 0 to 31 and
* 127 to 159, inclusive. However, we allow code points 9, 10
* and 13, which are the tab, line feed and carriage return
* respectively. 128 and above the code points map to multibyte
* UTF-8 representations.
*
*
* @note Fallback code adapted from utf8ToUnicode by Henri Sivonen and
* hsivonen@iki.fi at <http://iki.fi/hsivonen/php-utf8/> under the
* LGPL license. Notes on what changed are inside, but in general,
@@ -45,7 +45,7 @@ class HTMLPurifier_Encoder
* Once again, PHP 6 should solve all our problems.
*/
public static function cleanUTF8($str, $force_php = false) {
// UTF-8 validity is checked since PHP 4.3.5
// This is an optimization: if the string is already valid UTF-8, no
// need to do PHP stuff. 99% of the time, this will be the case.
@@ -54,31 +54,31 @@ class HTMLPurifier_Encoder
if (preg_match('/^[\x{9}\x{A}\x{D}\x{20}-\x{7E}\x{A0}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]*$/Du', $str)) {
return $str;
}
$mState = 0; // cached expected number of octets after the current octet
// until the beginning of the next UTF8 character sequence
$mUcs4 = 0; // cached Unicode character
$mBytes = 1; // cached expected number of octets in the current sequence
// original code involved an $out that was an array of Unicode
// codepoints. Instead of having to convert back into UTF-8, we've
// decided to directly append valid UTF-8 characters onto a string
// $out once they're done. $char accumulates raw bytes, while $mUcs4
// turns into the Unicode code point, so there's some redundancy.
$out = '';
$char = '';
$len = strlen($str);
for($i = 0; $i < $len; $i++) {
$in = ord($str{$i});
$char .= $str[$i]; // append byte to char
if (0 == $mState) {
// When mState is zero we expect either a US-ASCII character
// When mState is zero we expect either a US-ASCII character
// or a multi-octet sequence.
if (0 == (0x80 & ($in))) {
// US-ASCII, pass straight through.
if (($in <= 31 || $in == 127) &&
if (($in <= 31 || $in == 127) &&
!($in == 9 || $in == 13 || $in == 10) // save \r\t\n
) {
// control characters, remove
@@ -108,12 +108,12 @@ class HTMLPurifier_Encoder
$mBytes = 4;
} elseif (0xF8 == (0xFC & ($in))) {
// First octet of 5 octet sequence.
//
// This is illegal because the encoded codepoint must be
//
// This is illegal because the encoded codepoint must be
// either:
// (a) not the shortest form or
// (b) outside the Unicode range of 0-0x10FFFF.
// Rather than trying to resynchronize, we will carry on
// Rather than trying to resynchronize, we will carry on
// until the end of the sequence and let the later error
// handling code catch it.
$mUcs4 = ($in);
@@ -128,7 +128,7 @@ class HTMLPurifier_Encoder
$mState = 5;
$mBytes = 6;
} else {
// Current octet is neither in the US-ASCII range nor a
// Current octet is neither in the US-ASCII range nor a
// legal first octet of a multi-octet sequence.
$mState = 0;
$mUcs4 = 0;
@@ -144,13 +144,13 @@ class HTMLPurifier_Encoder
$tmp = $in;
$tmp = ($tmp & 0x0000003F) << $shift;
$mUcs4 |= $tmp;
if (0 == --$mState) {
// End of the multi-octet sequence. mUcs4 now contains
// the final Unicode codepoint to be output
// Check for illegal sequences and codepoints.
// From Unicode 3.1, non-shortest form is illegal
if (((2 == $mBytes) && ($mUcs4 < 0x0080)) ||
((3 == $mBytes) && ($mUcs4 < 0x0800)) ||
@@ -161,7 +161,7 @@ class HTMLPurifier_Encoder
// Codepoints outside the Unicode range are illegal
($mUcs4 > 0x10FFFF)
) {
} elseif (0xFEFF != $mUcs4 && // omit BOM
// check for valid Char unicode codepoints
(
@@ -196,7 +196,7 @@ class HTMLPurifier_Encoder
}
return $out;
}
/**
* Translates a Unicode codepoint into its corresponding UTF-8 character.
* @note Based on Feyd's function at
@@ -209,7 +209,7 @@ class HTMLPurifier_Encoder
* maintenance/generate-entity-file.php (although this is superior,
* due to its sanity checks).
*/
// +----------+----------+----------+----------+
// | 33222222 | 22221111 | 111111 | |
// | 10987654 | 32109876 | 54321098 | 76543210 | bit
@@ -221,17 +221,17 @@ class HTMLPurifier_Encoder
// +----------+----------+----------+----------+
// | 00000000 | 00011111 | 11111111 | 11111111 | Theoretical upper limit of legal scalars: 2097151 (0x001FFFFF)
// | 00000000 | 00010000 | 11111111 | 11111111 | Defined upper limit of legal scalar codes
// +----------+----------+----------+----------+
// +----------+----------+----------+----------+
public static function unichr($code) {
if($code > 1114111 or $code < 0 or
($code >= 55296 and $code <= 57343) ) {
// bits are set outside the "valid" range as defined
// by UNICODE 4.1.0
// by UNICODE 4.1.0
return '';
}
$x = $y = $z = $w = 0;
$x = $y = $z = $w = 0;
if ($code < 128) {
// regular ASCII character
$x = $code;
@@ -248,18 +248,18 @@ class HTMLPurifier_Encoder
$z = (($code >> 12) & 63) | 128;
$w = (($code >> 18) & 7) | 240;
}
}
}
}
// set up the actual character
$ret = '';
if($w) $ret .= chr($w);
if($z) $ret .= chr($z);
if($y) $ret .= chr($y);
$ret .= chr($x);
$ret .= chr($x);
return $ret;
}
/**
* Converts a string to UTF-8 based on configuration.
*/
@@ -290,7 +290,7 @@ class HTMLPurifier_Encoder
}
trigger_error('Encoding not supported, please install iconv', E_USER_ERROR);
}
/**
* Converts a string from UTF-8 based on configuration.
* @note Currently, this is a lossy conversion, with unexpressable
@@ -325,7 +325,7 @@ class HTMLPurifier_Encoder
}
trigger_error('Encoding not supported', E_USER_ERROR);
}
/**
* Lossless (character-wise) conversion of HTML to ASCII
* @param $str UTF-8 string to be converted to ASCII
@@ -372,13 +372,13 @@ class HTMLPurifier_Encoder
}
return $result;
}
/**
* This expensive function tests whether or not a given character
* encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
* fail this test, and require special processing. Variable width
* encodings shouldn't ever fail.
*
*
* @param string $encoding Encoding name to test, as per iconv format
* @param bool $bypass Whether or not to bypass the precompiled arrays.
* @return Array of UTF-8 characters to their corresponding ASCII,
@@ -419,7 +419,7 @@ class HTMLPurifier_Encoder
$encodings[$encoding] = $ret;
return $ret;
}
}